Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators

• URL: http://arxiv.org/abs/2407.07356v2
• Date: Wed, 19 Mar 2025 10:22:15 GMT
• Title: Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators
• Authors: Wentao Zhang, Junliang Guo, Tianyu He, Li Zhao, Linli Xu, Jiang Bian,
• Abstract summary: We explore utilizing visual signals as a new interface for models to interact with the environment.<n>We find that the model emerges a zero-shot capability to infer the semantics from a demonstration video, and imitate the semantics to an unseen scenario.<n>Results show that our models can generate high-quality video clips that accurately align with the semantic guidance provided by the demonstration videos.
• Score: 46.40277880351059
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: People interact with the real-world largely dependent on visual signal, which are ubiquitous and illustrate detailed demonstrations. In this paper, we explore utilizing visual signals as a new interface for models to interact with the environment. Specifically, we choose videos as a representative visual signal. And by training autoregressive Transformers on video datasets in a self-supervised objective, we find that the model emerges a zero-shot capability to infer the semantics from a demonstration video, and imitate the semantics to an unseen scenario. This allows the models to perform unseen tasks by watching the demonstration video in an in-context manner, without further fine-tuning. To validate the imitation capacity, we design various evaluation metrics including both objective and subjective measures. The results show that our models can generate high-quality video clips that accurately align with the semantic guidance provided by the demonstration videos, and we also show that the imitation capacity follows the scaling law. Code and models have been open-sourced.

Related papers

• SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning [50.98341607245458]
  Masked video modeling is an effective paradigm for video self-supervised learning (SSL) This paper introduces a novel SSL approach for video representation learning, dubbed as SMILE, by infusing both spatial and motion semantics. We establish a new self-supervised video learning paradigm capable of learning strong video representations without requiring any natural video data.
  arXiv  Detail & Related papers  (2025-04-01T08:20:55Z)
• Video Creation by Demonstration [59.389591010842636]
  We present $delta$-Diffusion, a self-supervised training approach that learns from unlabeled videos by conditional future frame prediction. By leveraging a video foundation model with an appearance bottleneck design on top, we extract action latents from demonstration videos for conditioning the generation process. Empirically, $delta$-Diffusion outperforms related baselines in terms of both human preference and large-scale machine evaluations.
  arXiv  Detail & Related papers  (2024-12-12T18:41:20Z)
• Grounding Video Models to Actions through Goal Conditioned Exploration [29.050431676226115]
  We propose a framework that uses trajectory level action generation in combination with video guidance to enable an agent to solve complex tasks. We show how our approach is on par with or even surpasses multiple behavior cloning baselines trained on expert demonstrations.
  arXiv  Detail & Related papers  (2024-11-11T18:43:44Z)
• Towards Multi-Task Multi-Modal Models: A Video Generative Perspective [5.495245220300184]
  This thesis chronicles our endeavor to build multi-task models for generating videos and other modalities under diverse conditions. We unveil a novel approach to mapping bidirectionally between visual observation and interpretable lexical terms. Our scalable visual token representation proves beneficial across generation, compression, and understanding tasks.
  arXiv  Detail & Related papers  (2024-05-26T23:56:45Z)
• Any-point Trajectory Modeling for Policy Learning [64.23861308947852]
  We introduce Any-point Trajectory Modeling (ATM) to predict future trajectories of arbitrary points within a video frame. ATM outperforms strong video pre-training baselines by 80% on average. We show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology.
  arXiv  Detail & Related papers  (2023-12-28T23:34:43Z)
• Sequential Modeling Enables Scalable Learning for Large Vision Models [120.91839619284431]
  We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. We define a common format, "visual sentences", in which we can represent raw images and videos as well as annotated data sources.
  arXiv  Detail & Related papers  (2023-12-01T18:59:57Z)
• Helping Hands: An Object-Aware Ego-Centric Video Recognition Model [60.350851196619296]
  We introduce an object-aware decoder for improving the performance of ego-centric representations on ego-centric videos. We show that the model can act as a drop-in replacement for an ego-awareness video model to improve performance through visual-text grounding.
  arXiv  Detail & Related papers  (2023-08-15T17:58:11Z)
• Masked World Models for Visual Control [90.13638482124567]
  We introduce a visual model-based RL framework that decouples visual representation learning and dynamics learning. We demonstrate that our approach achieves state-of-the-art performance on a variety of visual robotic tasks.
  arXiv  Detail & Related papers  (2022-06-28T18:42:27Z)
• Video Summarization Based on Video-text Modelling [0.0]
  We propose a multimodal self-supervised learning framework to obtain semantic representations of videos. We also introduce a progressive video summarization method, where the important content in a video is pinpointed progressively to generate better summaries. An objective evaluation framework is proposed to measure the quality of video summaries based on video classification.
  arXiv  Detail & Related papers  (2022-01-07T15:21:46Z)
• MERLOT: Multimodal Neural Script Knowledge Models [74.05631672657452]
  We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech. MERLOT exhibits strong out-of-the-box representations of temporal commonsense, and achieves state-of-the-art performance on 12 different video QA datasets. On Visual Commonsense Reasoning, MERLOT answers questions correctly with 80.6% accuracy, outperforming state-of-the-art models of similar size by over 3%.
  arXiv  Detail & Related papers  (2021-06-04T17:57:39Z)
• Improving Generation and Evaluation of Visual Stories via Semantic Consistency [72.00815192668193]
  Given a series of natural language captions, an agent must generate a sequence of images that correspond to the captions. Prior work has introduced recurrent generative models which outperform synthesis text-to-image models on this task. We present a number of improvements to prior modeling approaches, including the addition of a dual learning framework.
  arXiv  Detail & Related papers  (2021-05-20T20:42:42Z)
• Video SemNet: Memory-Augmented Video Semantic Network [14.64546899992196]
  We propose a machine learning approach to capture the narrative elements in movies by bridging the gap between the low-level data representations and semantic aspects of the visual medium. We present a Memory-Augmented Video Semantic Network, called Video SemNet, to encode the semantic descriptors and learn an embedding for the video. We demonstrate that our model is able to predict genres and IMDB ratings with a weighted F-1 score of 0.72 and 0.63 respectively.
  arXiv  Detail & Related papers  (2020-11-22T01:36:37Z)
• Watch and Learn: Mapping Language and Noisy Real-world Videos with Self-supervision [54.73758942064708]
  We teach machines to understand visuals and natural language by learning the mapping between sentences and noisy video snippets without explicit annotations. For training and evaluation, we contribute a new dataset ApartmenTour' that contains a large number of online videos and subtitles.
  arXiv  Detail & Related papers  (2020-11-19T03:43:56Z)
• Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language [148.0843278195794]
  We propose a new model architecture for learning multi-modal neuro-symbolic representations for video captioning. Our approach uses a dictionary learning-based method of learning relations between videos and their paired text descriptions.
  arXiv  Detail & Related papers  (2020-11-18T20:21:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.